Image super-resolution using registration of wavelet multi-scale components with affine transformation

Yasutaka Matsuo, Ryoki Takada, Shinya Iwasaki, Jiro Katto

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

We propose a novel image super-resolution method from digital cinema to 8K ultra high-definition television using registration of wavelet multi-scale components with affine transformation. The proposed method features that an original image is divided into signal and noise components by the wavelet soft-shrinkage with detection of white noise level. The signal component enhances resolution by registration between a signal component and its wavelet multi-scale components with affine transformation and parameters optimization. The affine transformation enhances super-resolution image quality because it increases registration candidates. The noise component enhances resolution with power control considering cinema noise representation. Super-resolution image outputs by synthesis of super-resolved signal and noise components. Experiments show that the proposed method has objectively better PSNR measurement and subjectively better appearance in comparison with conventional super-resolution methods.

Original languageEnglish
Title of host publicationProceedings - 2013 IEEE International Symposium on Multimedia, ISM 2013
Pages279-282
Number of pages4
DOIs
Publication statusPublished - 2013 Dec 1
Event15th IEEE International Symposium on Multimedia, ISM 2013 - Anaheim, CA, United States
Duration: 2013 Dec 92013 Dec 11

Publication series

NameProceedings - 2013 IEEE International Symposium on Multimedia, ISM 2013

Conference

Conference15th IEEE International Symposium on Multimedia, ISM 2013
CountryUnited States
CityAnaheim, CA
Period13/12/913/12/11

Keywords

  • Affine transformation
  • Digital cinema
  • Image super-resolution
  • Registration
  • Ultra high-definition television

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Human-Computer Interaction
  • Software

Fingerprint Dive into the research topics of 'Image super-resolution using registration of wavelet multi-scale components with affine transformation'. Together they form a unique fingerprint.

  • Cite this

    Matsuo, Y., Takada, R., Iwasaki, S., & Katto, J. (2013). Image super-resolution using registration of wavelet multi-scale components with affine transformation. In Proceedings - 2013 IEEE International Symposium on Multimedia, ISM 2013 (pp. 279-282). [6746805] (Proceedings - 2013 IEEE International Symposium on Multimedia, ISM 2013). https://doi.org/10.1109/ISM.2013.53